Many computer vision questions on AI-900 come down to one decision: how much detail about the image does the scenario need? Is one answer for the whole image enough, does it need the location of each object, or does it need the exact shape of each object? Those three levels are image classification, object detection and semantic segmentation.
Free account
Keep reading for free
Create a free StudyToCert account to read the rest of this lesson: 5 more sections, 4 key terms, a real-world example, an exam tip and self-check questions. Every lesson, lab and practice test is free with an account.